def prepare(self):
url = 'http://yann.lecun.com/exdb/mnist/'
train_files = {'target': 'train-images-idx3-ubyte.gz',
'label': 'train-labels-idx1-ubyte.gz'}
test_files = {'target': 't10k-images-idx3-ubyte.gz',
'label': 't10k-labels-idx1-ubyte.gz'}
files = train_files if self.train else test_files
data_path = get_file(url + files['target'])
label_path = get_file(url + files['label'])
self.data = self._load_data(data_path)
self.label = self._load_label(label_path)
def prepare(self):
url = "http://yann.lecun.com/exdb/mnist/"
train_files = {
"target": "train-images-idx3-ubyte.gz",
"label": "train-labels-idx1-ubyte.gz",
}
test_files = {
"target": "t10k-images-idx3-ubyte.gz",
"label": "t10k-labels-idx1-ubyte.gz"
}
files = train_files if self.train else test_files
data_path = get_file(url + files["target"])
label_path = get_file(url + files["label"])
self.data = self._load_data(data_path)
self.label = self._load_label(label_path)
def prepare(self):
url = 'https://www.cs.toronto.edu/~kriz/cifar-100-python.tar.gz'
self.data, self.label = load_cache_npz(url, self.train)
if self.data is not None:
return
filepath = get_file(url)
if self.train:
self.data = self._load_data(filepath, 'train')
self.label = self._load_label(filepath, 'train')
else:
self.data = self._load_data(filepath, 'test')
self.label = self._load_label(filepath, 'test')
self.data = self.data.reshape(-1, 3, 32, 32)
save_cache_npz(self.data, self.label, url, self.train)
def prepare(self):
url = 'https://www.cs.toronto.edu/~kriz/cifar-10-python.tar.gz'
self.data, self.label = load_cache_npz(url, self.train)
if self.data is not None:
return
filepath = get_file(url)
if self.train:
self.data = np.empty((50000, 3 * 32 * 32))
self.label = np.empty((50000), dtype=np.int)
for i in range(5):
self.data[i * 10000:(i + 1) * 10000] = self._load_data(
filepath, i + 1, 'train')
self.label[i * 10000:(i + 1) * 10000] = self._load_label(
filepath, i + 1, 'train')
else:
self.data = self._load_data(filepath, 5, 'test')
self.label = self._load_label(filepath, 5, 'test')
self.data = self.data.reshape(-1, 3, 32, 32)
save_cache_npz(self.data, self.label, url, self.train)
def get_shakespear():
url = 'https://raw.githubusercontent.com/karpathy/char-rnn/master/data/tinyshakespeare/input.txt'
file_name = 'shakespear.txt'
path = get_file(url, file_name)
with open(path, 'r') as f:
data = f.read()
chars = list(data)
char_to_id = {}
id_to_char = {}
for word in data:
if word not in char_to_id:
new_id = len(char_to_id)
char_to_id[word] = new_id
id_to_char[new_id] = word
indices = np.array([char_to_id[c] for c in chars])
return indices, char_to_id, id_to_char
def prepare(self):
url = 'https://raw.githubusercontent.com/karpathy/char-rnn/master/data/tinyshakespeare/input.txt'
file_name = 'shakespear.txt'
path = get_file(url, file_name)
with open(path, 'r') as f:
data = f.read()
chars = list(data)
char_to_id = {}
id_to_char = {}
for word in data:
if word not in char_to_id:
new_id = len(char_to_id)
char_to_id[word] = new_id
id_to_char[new_id] = word
indices = np.array([char_to_id[c] for c in chars])
self.data = indices[:-1]
self.label = indices[1:]
self.char_to_id = char_to_id
self.id_to_char = id_to_char
def __init__(self, pretrained=False) -> None:
super().__init__()
self.conv1_1 = L.Conv2d(64, kernel_size=3, stride=1, pad=1)
self.conv1_2 = L.Conv2d(64, kernel_size=3, stride=1, pad=1)
self.conv2_1 = L.Conv2d(128, kernel_size=3, stride=1, pad=1)
self.conv2_2 = L.Conv2d(128, kernel_size=3, stride=1, pad=1)
self.conv3_1 = L.Conv2d(256, kernel_size=3, stride=1, pad=1)
self.conv3_2 = L.Conv2d(256, kernel_size=3, stride=1, pad=1)
self.conv3_3 = L.Conv2d(256, kernel_size=3, stride=1, pad=1)
self.conv4_1 = L.Conv2d(512, kernel_size=3, stride=1, pad=1)
self.conv4_2 = L.Conv2d(512, kernel_size=3, stride=1, pad=1)
self.conv4_3 = L.Conv2d(512, kernel_size=3, stride=1, pad=1)
self.conv5_1 = L.Conv2d(512, kernel_size=3, stride=1, pad=1)
self.conv5_2 = L.Conv2d(512, kernel_size=3, stride=1, pad=1)
self.conv5_3 = L.Conv2d(512, kernel_size=3, stride=1, pad=1)3
self.fc6 = L.Linear(4096)
self.fc7 = L.Linear(4096)
self.fc8 = L.Linear(1000)
if pretrained:
weights_path = utils.get_file(VGG16.WEIGHT_PATH)
self.load_weights(weights_path)
def __init__(self, pretrained=False):
super().__init__()
self.conv1_1 = L.Conv2d(3, 64, 3, 1, 1)
self.conv1_2 = L.Conv2d(64, 64, 3, 1, 1)
self.conv2_1 = L.Conv2d(64, 128, 3, 1, 1)
self.conv2_2 = L.Conv2d(128, 128, 3, 1, 1)
self.conv3_1 = L.Conv2d(128, 256, 3, 1, 1)
self.conv3_2 = L.Conv2d(256, 256, 3, 1, 1)
self.conv3_3 = L.Conv2d(256, 256, 3, 1, 1)
self.conv4_1 = L.Conv2d(256, 512, 3, 1, 1)
self.conv4_2 = L.Conv2d(512, 512, 3, 1, 1)
self.conv4_3 = L.Conv2d(512, 512, 3, 1, 1)
self.conv5_1 = L.Conv2d(512, 512, 3, 1, 1)
self.conv5_2 = L.Conv2d(512, 512, 3, 1, 1)
self.conv5_3 = L.Conv2d(512, 512, 3, 1, 1)
self.fc6 = L.Linear(4096)
self.fc7 = L.Linear(4096)
self.fc8 = L.Linear(1000)
if pretrained:
weights_path = utils.get_file(VGG16.WEIGHTS_PATH)
self.load_weights(weights_path)
def __init__(self, n_layers=152, pretrained=False):
super().__init__()
if n_layers == 50:
block = [3, 4, 6, 3]
elif n_layers == 101:
block = [3, 4, 23, 3]
elif n_layers == 152:
block = [3, 8, 36, 3]
else:
raise ValueError('The n_layers argument should be either 50, 101,'
' or 152, but {} was given.'.format(n_layers))
self.conv1 = L.Conv2d(3, 64, 7, 2, 3)
self.bn1 = L.BatchNorm()
self.res2 = BuildingBlock(block[0], 64, 64, 256, 1)
self.res3 = BuildingBlock(block[1], 256, 128, 512, 2)
self.res4 = BuildingBlock(block[2], 512, 256, 1024, 2)
self.res5 = BuildingBlock(block[3], 1024, 512, 2048, 2)
self.fc6 = L.Linear(1000)
if pretrained:
weights_path = utils.get_file(ResNet.WEIGHTS_PATH.format(n_layers))
self.load_weights(weights_path)
def labels():
url = 'https://gist.githubusercontent.com/yrevar/942d3a0ac09ec9e5eb3a/raw/238f720ff059c1f82f368259d1ca4ffa5dd8f9f5/imagenet1000_clsidx_to_labels.txt'
path = get_file(url)
with open(path, 'r') as f:
labels = eval(f.read())
return labels
def download_mnist(self):
for v in MNIST.key_file.values():
get_file(MNIST.url_base + v)
